Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/code-payments/code-android-app/fetch-protosnpx skills add code-payments/code-android-app --skill fetch-protosgit clone --depth 1 https://github.com/code-payments/code-android-appWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00042 | $0.03211 |
| Opus 5 | $0.00021 | $0.01605 |
| Sonnet 5 | $0.00008 | $0.00642 |
| Haiku 4.5 | $0.00004 | $0.00321 |
Grade A, and why
fetch-protos scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fetch Protos
The protos are no longer vendored here. Both contracts arrive as published artifacts, so "fetching" is bumping a version pin and reacting to what the new version changed.
| Target | Artifact | Client repo | Upstream contract |
|---|---|---|---|
flipcash |
com.flipcash:flipcash2-client-protocol |
code-payments/flipcash2-client-protocol |
code-payments/flipcash2-protobuf-api |
opencode |
com.flipcash:ocp-client-protocol |
code-payments/ocp-client-protocol |
code-payments/ocp-protobuf-api |
Pre-flight context
- Pinned versions: !
grep -E "^(ocp|flipcash2)-client-protocol = " gradle/libs.versions.toml - Local override: !
grep -E "^protoLocalRoot" local.properties 2>/dev/null || echo "none — building against the pins above" - Git status: !
git status --short gradle/libs.versions.toml services/
Input
Parse $ARGUMENTS to determine targets and an optional version.
Rules:
- Known targets:
flipcash,opencode - If no targets specified, check both
- A semver-looking string as the last argument is the version to move to; without one, use the latest release
- Examples:
/fetch-protos→ check both artifacts for newer releases/fetch-protos flipcash→ flipcash only, latest release/fetch-protos opencode 0.2.0→ opencode at 0.2.0
Steps
Step 1 — Find the release
gh release list --repo code-payments/<ocp|flipcash2>-client-protocol --limit 10
Compare against the pin in gradle/libs.versions.toml. If the pinned version is
already the latest and no version was requested, say so and stop.
If the contract change you want has not been released, do not reach for a release.
Publishing is for CI release builds; Maven Central will not take a version number
twice, so cutting one to try a field burns a real version. Build against the client
checkout instead, by adding the workspace root to local.properties:
protoLocalRoot=/Users/you/dev/bmcreations/code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 329 lines · 42 tokens per session scan A eeec73cfa3f3
fetch-protos is a skill published in the GitHub repository code-payments/code-android-app (23 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 3,211 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
orca-emulator-android
Control an Android emulator / device from inside Orca using the orca CLI. Use for listing/booting AVDs, taps, swipes, typing, hardware buttons (incl. Back and Recents), rotation, app install/launch, runtime permissions, the accessibility tree, and logcat — driving a real adb-connected device or emulator.…
speckit-analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
add-sample
Create a SamplesApp sample page with correct theming and attributes. Use when adding UI samples for controls.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…
android-tombstone-symbolication
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…